17 citations · 58 across the 19 of their papers we have counts for
16 papers · 1 filter
InfoSync: Information Synchronization across Multilingual Semi-structured Tables
Siddharth Khincha, Chelsi Jain, Vivek Gupta +2
Information Synchronization of semi-structured data across languages is challenging. For instance, Wikipedia tables in one language should be synchronized across languages. To addr…
Leveraging Data Recasting to Enhance Tabular Reasoning
Aashna Jena, Vivek Gupta, Manish Shrivastava +1
Creating challenging tabular inference data is essential for learning complex reasoning. Prior work has mostly relied on two data generation strategies. The first is human annotati…
Realistic Data Augmentation Framework for Enhancing Tabular Reasoning
Dibyakanti Kumar, Vivek Gupta, Soumya Sharma +1
Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully aut…
Enhancing Tabular Reasoning with Pattern Exploiting Training
Abhilash Reddy Shankarampeta, Vivek Gupta, Shuo Zhang
Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using…
Unsupervised Contextualized Document Representation
Ankur Gupta, Vivek Gupta
Several NLP tasks need the effective representation of text documents. Arora et. al., 2017 demonstrate that simple weighted averaging of word vectors frequently outperforms neural…
RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing
Vivek Gupta, Akshat Shrivastava, Adithya Sagar +2
While large pre-trained language models accumulate a lot of knowledge in their parameters, it has been demonstrated that augmenting it with non-parametric retrieval-based memory ha…
TabPert: An Effective Platform for Tabular Perturbation
Nupur Jain, Vivek Gupta, Anshul Rai +1
To truly grasp reasoning ability, a Natural Language Inference model should be evaluated on counterfactual data. TabPert facilitates this by assisting in the generation of such cou…
Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning
Vivek Gupta, Riyaz A. Bhat, Atreya Ghosal +3
Neural models command state-of-the-art performance across NLP tasks, including ones involving "reasoning". Models claiming to reason about the evidence presented to them should att…
On Long-Tailed Phenomena in Neural Machine Translation
Vikas Raunak, Siddharth Dalmia, Vivek Gupta +1
State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens, tackling which remains a major challenge. The analysis of long-tailed phenom…
P-SIF: Document Embeddings Using Partition Averaging
Vivek Gupta, Ankit Saw, Pegah Nokhiz +3
Simple weighted averaging of word vectors often yields effective representations for sentences which outperform sophisticated seq2seq neural models in many tasks. While it is desir…
INFOTABS: Inference on Tables as Semi-structured Data
Vivek Gupta, Maitrey Mehta, Pegah Nokhiz +1
In this paper, we observe that semi-structured tabulated text is ubiquitous; understanding them requires not only comprehending the meaning of text fragments, but also implicit rel…
Improving Document Classification with Multi-Sense Embeddings
Vivek Gupta, Ankit Saw, Pegah Nokhiz +2
Efficient representation of text documents is an important building block in many NLP tasks. Research on long text categorization has shown that simple weighted averaging of word v…
On Dimensional Linguistic Properties of the Word Embedding Space
Vikas Raunak, Vaibhav Kumar, Vivek Gupta +1
Word embeddings have become a staple of several natural language processing tasks, yet much remains to be understood about their properties. In this work, we analyze word embedding…
Simple and Effective Dimensionality Reduction for Word Embeddings
Vikas Raunak
Word embeddings have become the basic building blocks for several natural language processing and information retrieval tasks. Pre-trained word embeddings are used in several downs…
User Bias Removal in Review Score Prediction
Rahul Wadbude, Vivek Gupta, Dheeraj Mekala +1
Review score prediction of text reviews has recently gained a lot of attention in recommendation systems. A major problem in models for review score prediction is the presence of n…
SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations
Dheeraj Mekala, Vivek Gupta, Bhargavi Paranjape +1
We present a feature vector formation technique for documents - Sparse Composite Document Vector (SCDV) - which overcomes several shortcomings of the current distributional paragra…